CN102527737B - Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill - Google Patents
Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill Download PDFInfo
- Publication number
- CN102527737B CN102527737B CN201210012408.1A CN201210012408A CN102527737B CN 102527737 B CN102527737 B CN 102527737B CN 201210012408 A CN201210012408 A CN 201210012408A CN 102527737 B CN102527737 B CN 102527737B
- Authority
- CN
- China
- Prior art keywords
- lambda
- cold
- rolling mill
- data
- efficiency coefficient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Control Of Metal Rolling (AREA)
Abstract
The invention relates to an offline self-learning system for a strip shape control efficiency coefficient of a cold-rolling mill. The offline self-learning system comprises an offline self-learning parameter setting module, a cold-rolling mill input-output process data reading module, a process data sequential processing module, a data-driven strip shape control function mechanism modeling module, a cold-rolling mill strip shape control efficiency coefficient computing module and a computed result evaluating and processing module which are sequentially connected, and the modules are used for preliminarily screening and sequentially processing data according to tension groups before rolling in the input-output process of the cold-rolling mill, building a data-driven strip shape control function mechanism model and an objective optimization function, and computing the cold-rolling mill strip shape control efficiency coefficient for minimizing the objective optimization function. The offline self-learning system provides an effective way which can be used for offline self-learning of the high-precision cold-rolling mill strip shape control efficiency coefficient, thereby solving the technical problems that strip shape control precision of a cold-rolled steel strip product is low, and even production accidents of strip breakage stop are caused in traditional cold-rolled steel strip production.
Description
Technical field
The present invention relates to cold-strip steel field, relate in particular to a kind of offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill.
Background technology
Along with the develop rapidly of domestic equipment manufacture, cold-strip steel user requires also more and more higher to the strip shape quality of product, especially show the industries such as high-grade automobile, IT industry and household electrical appliance.Improve that product strip shape quality has become that cold-strip steel enterprise increases economic efficiency and one of the important channel of core competitiveness.Cold-rolled strip steel shape control technology is a guardian technique that merges multi-subject knowledge, high complexity, relate to the professional knowledge of multiple subjects such as technique, equipment, hydraulic pressure, electrical control and computer, need the collaborative optimal design work of carrying out each control functional module of each specialty.Cold rolled sheet shape control technology is caused import cold rolled sheet shape control system expensive by offshore company monopolizes always, even become and can not guarantee that system well moves after specification at product owing to not grasping core technology after high price import, the production domesticization research and development of therefore carrying out cold rolled sheet shape control core technology are imperative.In order to strengthen the plate shape control ability of cold-rolling mill, modern cold rolling mill generally has plurality of plate-shape control measures, as cooling in depress inclining, the positive and negative roller of working roll, the positive roller of intermediate calender rolls, roll shifting and injection etc.In the time that cold-rolled strip steel shape control system puts into operation, plate shape automatic control system need to consider the ability of regulation and control of each plate shape control measures, is calculated and is made each plate shape control measures cooperatively interact to reach the control effect of eliminating to greatest extent plate shape deviation by pool.Therefore, the accurate evaluation of the ability of regulation and control to each plate shape control measures, that is to say that whether can obtain high-precision cold-rolling mill shape regulation and control efficiency coefficient just becomes a key factor that affects plate shape control effect quality.
The application system having for calculating cold-rolling mill shape regulation and control efficiency coefficient is mainly divided into finite element numerical calculating, milling train experiment and online self study according to principle.Due to different cold-rolling mill shape regulating and controlling mechanisms on exit plate shape to affect mechanism very complicated, unknown disturbances many factors in model, milling train working condition is also constantly to change, and is therefore difficult to accurately calculate high-precision cold-rolling mill shape regulation and control efficiency coefficient by machine rational methods such as traditional roll elastic deformation theory, rolled piece 3 D deformation theories; This is also the bottleneck running into while solving such problem by finite element numerical computational methods.In actual strip-rolling production process, cold-rolling mill shape regulation and control efficiency coefficient also can be subject to the impact of many operation of rolling parameters, as strip width, roll-force, gloss level of roll and roller temperature etc.; Different size with the corresponding different cold-rolling mill shapes regulation and control of steel efficiency coefficient, even identical specification with steel under different operating modes (for example different rolling tensile force conditions) its cold-rolling mill shape regulation and control efficiency coefficient also can change, thereby test by milling train the cold-rolling mill shape obtaining and regulates and controls efficiency coefficient and aspect precision, also have larger problem.On the other hand, use online self learning system can improve to a certain extent the precision of regulation and control efficiency coefficient, but because online plate deformation is by the coefficient result of several plate shape regulating and controlling mechanisms, each regulating and controlling mechanism intercouples on the impact of plate shape, and online self learning system can be controlled the harsh requirement of system real time, at present existing online self learning system can not regulate and control efficiency coefficient to cold-rolling mill shape and carry out accurate decomposition, thereby the online self study result obtaining is unsatisfactory, it is poorer to become even sometimes.
On the other hand, in the operation of rolling, can produce a lot of milling train input/output procedure data, in these data, contain abundant rolling information.If can rationally utilize these process datas to carry out off-line self study, just can obtain the input/output relation in real milling train production process, thereby obtain high-precision cold-rolling mill shape regulation and control efficiency coefficient.Meanwhile, the requirement of real-time restriction of the uncontrolled system of off-line self study, can design and utilize the complicated self-learning algorithm of abundant group of process data to carry out the off-line self study of cold-rolling mill shape regulation and control efficiency coefficient, while effectively having avoided sample data very few, exceptional data point causes the generation of computational solution precision variation phenomenon.Therefore, research and development offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill is a feasibility technical scheme that can further improve cold-rolled strip steel shape control quality.
Summary of the invention
Technical problem to be solved by this invention is: a kind of offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill is provided; this system can significantly improve the precision of cold-rolling mill shape regulation and control efficiency coefficient; can solve well in traditional cold rolled strip steel production because deviation between cold-rolling mill shape regulation and control efficiency coefficient calculated value and actual value is larger simultaneously, can cause the technical problem that cold-rolled steel strip products plate shape control accuracy is not high, tape break stop production accident even occurs after the not high efficiency coefficient of precision is applied to closed loop plat control system.
The present invention solves its technical problem and adopts following technical scheme:
Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill provided by the invention, comprise: the plate shape control action modelling by mechanism module of off-line self study parameter setting module, cold-rolling mill input/output procedure data read module, process data sequential processing module, data-driven, cold-rolling mill shape regulation and control efficiency coefficient computing module, result of calculation are passed judgment on and processing module, and they are linked in sequence successively; Described module is all by carrying out data Preliminary screening and sequential processing to cold-rolling mill input/output procedure data according to rolling forward pull group, set up plate shape control action mechanism model and objective optimization function based on data-driven, Mill shape regulation and control efficiency coefficient when calculating makes objective optimization function get minimum of a value, realizes the self study of High Precision Cold Rolling Mill plate shape regulation and control efficiency coefficient off-line.
Described off-line self study parameter setting module, this module, for realizing the initial parameter set-up function of off-line self learning system, comprising: band steel specification, rolling forward pull group, importing creation data group are counted Num.
Described cold-rolling mill input/output procedure data read module, this module is for receiving the parameter band steel specification that described off-line self study parameter setting module sets, rolling forward pull group, import creation data group and count Num, according to receiving parameter band steel specification, rolling forward pull group, importing creation data group counts and in Num slave plate shape Computer Database, reads the cold-rolling mill input/output procedure data for this off-line self study, the cold-rolling mill input/output procedure data that read are to meet the selected Num group data with steel specification and rolling forward pull group condition simultaneously, each group data inclusion information has: the regulated quantity of the online regulation device of each plate shape in corresponding control cycle, rolling forward pull size in corresponding control cycle, belt plate shape deviation profile signal when corresponding control cycle starts, the sequential numbering DataID of corresponding control cycle.
In above-mentioned cold-rolling mill input/output procedure data read module, in plate shape Computer Database, the assignment rule of the sequential of corresponding control cycle numbering DataID is: according to acquisition time sequencing, process data is carried out to process data numbering, the DataID=1 of first control cycle, the DataID=2 of second control cycle,, by that analogy; When causing the cold rolling roll coil of strip not continue to stablize high-speed rolling due to acceleration and deceleration or roll change reason, temporarily stop said process data storage procedure; In the time recovering to stablize high-speed rolling, proceed process data storage, if and the DataID=i of last group process data of last process data storage, the storage of this secondary data starts to proceed storage according to acquisition time sequencing from DataID=i+2, the DataID value of follow-up each group of process data is respectively i+3,, by that analogy.
Described process data sequential processing module, the group of the Num for this off-line self study cold-rolling mill input/output procedure data that this module reads for receiving described cold-rolling mill input/output procedure data read module, and the sequential numbering DataID value according to each group of data is carried out further sequential processing to Num group process data, processing rule is: from above-mentioned Num group process data, those minimum group data of DataID value start, if being respectively two groups of process datas of i and i+1, DataID value belongs to above-mentioned Num group process data simultaneously, according to the ascending order of DataID value by u
ij(i ∈ 1,2,3 ..., j=1 ..., m) assignment is to U
kj(k=1 ..., N, j=1 ..., m), simultaneously by δ
ij-δ
(i+1) jassignment is to F
kj(k=1 ..., N, j=1 ..., m), here m represents the online regulation device number of plate shape of cold-rolling mill configuration, and N carries out to effective cold-rolling mill input/output procedure data the data amount check obtaining after sequential processing in this step.
The plate shape control action modelling by mechanism module of described data-driven, this module is for receiving by process data U after the sequential processing of described process data sequential processing module output
kj(k=1 ..., N; J=1 ..., m) and F
kj(k=1 ..., N; J=1 ..., m), set up the following plate shape control action mechanism model based on data-driven:
In formula: E
kj(k=1 ..., m; J=1 ..., be n) the plate shape Mill shape regulation and control efficiency coefficient of the online regulation device of k kind plate shape at j plate shape characteristic point place, n is the plate shape characteristic point number of roll with steel here; r
kj(k=1 ..., N; J=1 ..., n) representing that in model, k group cold-rolling mill input/output procedure data are in the random error at j effective plate shape measurement characteristic point place, it obeys random normal distribution.
In the plate shape control action modelling by mechanism module of above-mentioned data-driven, effective measuring section number that the plate shape characteristic point number of roll with steel can laterally cover contact plate profile instrument with steel by roll is determined.
Described cold-rolling mill shape regulation and control efficiency coefficient computing module, the plate shape control action mechanism model based on data-driven that the plate shape control action modelling by mechanism module of this module based on described data-driven provides, set up the objective optimization function of following cold-rolling mill shape regulation and control efficiency coefficient off-line self-learning method:
Then cold-rolling mill shape regulation and control efficiency coefficient E while utilizing least-squares algorithm calculating objective optimization function J to get minimum of a value
kj(k=1 ..., m; J=1 ..., n).
In above-mentioned cold-rolling mill shape regulation and control efficiency coefficient computing module, cold-rolling mill shape regulation and control efficiency coefficient E while utilizing least-squares algorithm calculating objective optimization function J to get minimum of a value
kjtime,
Adopt the following direct inversion calculation algorithm of routine:
Or,
Adopt following matrix Orthogonal Decomposition algorithm:
First by U
ij(i=1 ..., N; J=1 ..., N × m dimension matrix m) forming carries out Gram-Schmit Orthogonal Decomposition:
Then utilize the matrix computations cold-rolling mill shape regulation and control efficiency coefficient matrix after Gram-Schmit Orthogonal Decomposition:
It is pointed out that matrix Orthogonal Decomposition algorithm is better than direct inversion calculation algorithm aspect computational accuracy, but the amount of calculation of matrix Orthogonal Decomposition algorithm is the twice of direct inversion calculation algorithm amount of calculation.
Described result of calculation is passed judgment on and processing module, will in the objective optimization function of cold-rolling mill shape regulation and control efficiency coefficient computing module described in the Mill shape regulation and control efficiency coefficient substitution before off-line learning, calculate functional value J before this off-line learning
1, then will in the objective optimization function of cold-rolling mill shape regulation and control efficiency coefficient computing module described in the Mill shape regulation and control efficiency coefficient substitution after off-line learning, calculate functional value J after off-line learning
2.If there is J
1>J
2illustrate that this off-line self study has improved the precision of Mill shape regulation and control efficiency coefficients, think that this off-line learning meets the requirements, preserve the machine result of calculation to plate shape Computer Database, replace original cold-rolling mill shape regulation and control efficiency coefficient, for the plate shape control of same specification belt steel rolling process later; Otherwise, illustrate that this off-line self study has not improved the precision of Mill shape regulation and control efficiency coefficients, this off-line self study is undesirable, after counting Num, the importing creation data group that now can select to increase described off-line self study parameter setting module re-starts an off-line self study, until obtain satisfied off-line self study result.
Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill provided by the invention, compared with prior art has the following advantages:
One. provide a kind of effective way that can calculate High Precision Cold Rolling Mill plate shape regulation and control efficiency coefficient.
Set up the plate shape control action mechanism model based on data-driven, and provided the objective optimization function of offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill; Cold-rolling mill shape regulation and control efficiency coefficient while utilizing least-squares algorithm to calculate objective optimization function to get minimum of a value, can improve the precision of cold-rolling mill shape regulation and control efficiency coefficient to greatest extent.
They are two years old. and can solve well in traditional cold rolled strip steel production because deviation between cold-rolling mill shape regulation and control efficiency coefficient calculated value and actual value is larger, can cause the technical problem that cold-rolled steel strip products plate shape control accuracy is not high, tape break stop production accident even occurs after the not high efficiency coefficient of precision is applied to closed loop plat control system.
Accompanying drawing explanation
Fig. 1 is the system architecture diagram of an example of the present invention.
Fig. 2 is the cold-rolling mill shape regulation and control efficiency coefficient off-line self study calculation flow chart of an example of the present invention.
Fig. 3 is the software system interface figure realizing according to the inventive method programming in this example.
Fig. 4 is off-line calculation front and back system board shape regulation and control coefficients deviation target function comparison diagram in this example.
The specific embodiment
Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill provided by the invention, this system is by carrying out data Preliminary screening and sequential processing to cold-rolling mill input/output procedure data according to rolling forward pull group, set up plate shape control action mechanism model and objective optimization function based on data-driven, Mill shape regulation and control efficiency coefficient when calculating makes objective optimization function get minimum of a value, realize the self study of cold-rolling mill shape regulation and control efficiency coefficient off-line, thereby improve the precision of cold-rolling mill shape regulation and control efficiency coefficient.
Below in conjunction with embodiment and accompanying drawing, the invention will be further described, but do not limit the present invention.
Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill provided by the invention, as shown in Figure 1, comprise: the plate shape mechanism of action MBM of off-line self study parameter setting module, cold-rolling mill input/output procedure data read module, process data sequential processing module, data-driven, cold-rolling mill shape regulation and control efficiency coefficient computing module, result of calculation are passed judgment on and processing module, and they are linked in sequence successively.
Off-line self study parameter setting module: for realizing the initial parameter set-up function of off-line self learning system, comprising: band steel specification, rolling forward pull group, importing creation data group are counted Num.
Cold-rolling mill input/output procedure data read module: the parameter band steel specification setting for receiving described off-line self study parameter setting module, rolling forward pull group, import creation data group and count Num, read the cold-rolling mill input/output procedure data for this off-line self study according in above-mentioned setting value slave plate shape Computer Database, the cold-rolling mill input/output procedure data that read are to meet the selected Num group data with steel specification and rolling forward pull group condition simultaneously, each group data inclusion information has: the regulated quantity of the online regulation device of each plate shape in corresponding control cycle, rolling forward pull size in corresponding control cycle, belt plate shape deviation profile signal when corresponding control cycle starts, the sequential numbering DataID of corresponding control cycle.In the present embodiment, in plate shape Computer Database, the assignment rule of the sequential of corresponding control cycle numbering DataID is: according to acquisition time sequencing, process data is carried out to process data numbering, the DataID=1 of first control cycle, the DataID=2 of second control cycle,, by that analogy.When causing the cold rolling roll coil of strip not continue to stablize high-speed rolling due to the reason such as acceleration and deceleration or roll change, temporarily stop said process data storage procedure; In the time recovering to stablize high-speed rolling, proceed process data storage, if and the DataID=i of last group process data of last process data storage, the storage of this secondary data starts to proceed storage according to acquisition time sequencing from DataID=i+2, the DataID value of follow-up each group of process data is respectively i+2, i+3,, by that analogy.
Process data sequential processing module: the group of the Num for this off-line self study cold-rolling mill input/output procedure data that read for receiving described cold-rolling mill input/output procedure data read module, and the sequential numbering DataID value according to each group of data is carried out further sequential processing to Num group process data, processing rule is: from above-mentioned Num group process data, those minimum group data of DataID value start, belong to above-mentioned Num group process data if DataID value is respectively two groups of process datas of i and i+1 simultaneously, according to the ascending order of DataID value by u
ij(i ∈ 1,2,3 ...; J=1 ..., m) assignment is to U
kj(k=1 ..., N; J=1 ..., m), simultaneously by δ
ij-δ
(i+1) jassignment is to F
kj(k=1 ..., N; J=1 ..., m); Here m represents the online regulation device number of plate shape of cold-rolling mill configuration, and N carries out to effective cold-rolling mill input/output procedure data the data amount check obtaining after sequential processing in this step.
The plate shape control action modelling by mechanism module of data-driven: for receiving by process data U after the sequential processing of described process data sequential processing module output
kj(k=1 ..., N; J=1 ..., m) and Fkj (k=1 ..., N; J=1 ..., m), set up the following plate shape control action mechanism model based on data-driven:
In formula: E
kj(k=1 ..., m; J=1, n) be the plate shape Mill shape regulation and control efficiency coefficient of the online regulation device of k kind plate shape at j plate shape characteristic point place, n is the plate shape characteristic point number of roll with steel here, and the effective measuring section number that laterally covers contact plate profile instrument by roll with steel in the present embodiment is determined; r
kj(k=1 ..., N; J=1 ..., n) representing that in model, k group cold-rolling mill input/output procedure data are in the random error at j effective plate shape measurement characteristic point place, it obeys random normal distribution.
Cold-rolling mill shape regulation and control efficiency coefficient computing module: the plate shape control action mechanism model based on data-driven that the plate shape control action modelling by mechanism module based on described data-driven provides, set up the objective optimization function J of following cold-rolling mill shape regulation and control efficiency coefficient off-line self-learning method:
When the present embodiment utilizes least-squares algorithm calculating objective optimization function J to get minimum of a value, cold-rolling mill shape regulation and control efficiency coefficient E
kj(k=1 ..., m; J=1 ..., n).
Described least-squares algorithm can be selected one of following two kinds of implementation algorithms:
A) conventional directly inversion calculation algorithm:
B) matrix Orthogonal Decomposition algorithm:
First by U
ij(i=1 ..., N; J=1 ..., N × m dimension matrix m) forming carries out Gram-Schmit Orthogonal Decomposition:
Then utilize the matrix computations cold-rolling mill shape regulation and control efficiency coefficient matrix after Gram-Schmit Orthogonal Decomposition:
Result of calculation is passed judgment on and processing module: will in the objective optimization function of cold-rolling mill shape regulation and control efficiency coefficient computing module described in the Mill shape regulation and control efficiency coefficient substitution before off-line learning, calculate functional value J before this off-line learning
1, then will in the objective optimization function of cold-rolling mill shape regulation and control efficiency coefficient computing module described in the Mill shape regulation and control efficiency coefficient substitution after off-line learning, calculate functional value J after off-line learning
2.If there is J
1>J
2illustrate that this off-line self study has improved the precision of Mill shape regulation and control efficiency coefficients, think that this off-line learning meets the requirements, preserve the machine result of calculation to plate shape Computer Database, replace original cold-rolling mill shape regulation and control efficiency coefficient, for the plate shape control of same specification belt steel rolling process later; Otherwise, illustrate that this off-line self study has not improved the precision of Mill shape regulation and control efficiency coefficients, this off-line self study is undesirable, after counting Num, the importing creation data group that now can select to increase described off-line self study parameter setting module re-starts an off-line self study, until obtain satisfied off-line self study result.
Can be used for four rollers, six roller single chassis or multi-frame tandem mills based on offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill of the present invention.Below take a single chassis six-high cluster mill as example, the product that this six-high cluster mill can rolling comprises common plate, high-strength steel, part stainless steel and silicon steel etc.The present embodiment rolling be middle high grade silicon steel, type is UCM milling train, plate shape control device comprises that roller declination, the positive and negative roller of working roll, the positive roller of intermediate calender rolls, intermediate roll shifting and emulsion section are cooling etc.Wherein intermediate roll shifting is to preset according to strip width, and adjusting principle is that intermediate calender rolls body of roll edge is alignd with steel edge portion, also can be considered to add a correction by operation side, is transferred to a rear holding position constant; Emulsion section is cooling has larger characteristic time lag.Thereby the plate shape control device of on-line control mainly contains three kinds of roller declinations, the positive and negative roller of working roll, the positive roller of intermediate calender rolls.Basic mechanical design feature index and the device parameter of this unit are:
Mill speed: Max900m/min, draught pressure: Max18000KN, maximum rolling force square: 140.3KN × m, batches forward pull: Max220KN, main motor current: 5500KW; Supplied materials thickness range: 1.8~2.5mm, supplied materials width range: 850~1280mm, outgoing gauge scope: 0.2mm~1.0mm;
Work roll diameter: 290~340mm, working roll height: 1400mm, intermediate calender rolls diameter: 440~500mm, intermediate calender rolls height: 1640mm, backing roll diameter: 1150~1250mm, backing roll height: 1400mm;
Every side work roll bending power :-280~350KN, every side intermediate calender rolls bending roller force: 0~500KN, the axial traversing amount of intermediate calender rolls :-120~120mm, auxiliary hydraulic system pressure: 14MPa, balance bending system pressure: 28MPa, press down system pressure: 28MPa.
Plate Profile Measuring System (being generally contact plate profile instrument) adopts ABB AB's plate shape roller of Sweden, this plate shape roller roller footpath 313mm, formed by solid steel axle, broad ways is divided into a measured zone every 52mm or 26mm, in each measured zone, the surrounding at measuring roller is uniform-distribution with four grooves to place magnetoelasticity power sensor vertically, and the outside of sensor is wrapped up by steel loop.Product specification in this example (thickness × width) is: 0.25mm × 1250mm, and in the middle of plate profile instrument, 20 measurement section width are 52mm, all the other two-sided measurement section width are 26mm.
As shown in Figure 2, the present embodiment carries out the specific works process of cold-rolling mill shape regulation and control efficiency coefficient off-line self study and is:
(1) initial parameter that completes off-line self learning system is set:
Selecting C# high-level language is program development language, and the integration environment adopts the Visual Studio2010 of Microsoft, the single chassis six-roll cold mill plate shape regulating and controlling mechanism efficiency coefficient off-line self learning system of Fig. 3 for developing according to the present invention.All belt steel product specifications with having comprised the rolling of single chassis six-roll cold mill in steel specification option hurdle in system, system again according to six-roll cold mill production system by rolling forward pull during according to high-speed rolling maximum rolling forward pull and minimum rolling forward pull be evenly divided into six groups: 100KN~120KN, 121KN~140KN, 141KN~160KN, 161KN~180KN, 181KN~200KN, 201KN~220KN.
As shown in Figure 3, the initial parameter of setting off-line self learning system is: rolling specs 0.25mm × 1250mm, tension force group 161KN~180KN, imports creation data group and count Num=1000.
(2) read cold-rolling mill input/output procedure data by plate shape Computer Database:
The cold-rolling mill input/output procedure data group number of collecting in the time of the cold-strip steel of rolling 0.25mm × 1250mm specification in this example is 200000 groups (that is the maximum of DataID is 200000), by these mass data storage, in plate shape Computer Database, database platform adopts Oracle9i.According to tension force group selected in previous step, in system interface, after click " importing data ", 1000 groups of process datas that meet initial parameter requirement are imported to plate shape regulation and control efficiency coefficient off-line self learning system by plate shape Computer Database.1000 groups of process datas that import in this example comprise: cold-rolling mill is stablized three kinds of device regulated quantity u of the interior roller declination of 1000 control cycles, the positive and negative roller of working roll, the positive roller of intermediate calender rolls of the cold-strip steel collection of high-speed rolling 0.25mm × 1250mm specification
i1, u
i2, u
i3(i ∈ 1 ..., 200000}); Rolling forward pull size T in these 1000 control cycles
i(i ∈ 1 ..., 200000}), unit is KN; Belt plate shape deviation profile signal δ when above-mentioned 1000 control cycles start
ij(i ∈ 1 ..., 200000}; J=1 ..., 20; Unit is plate shape international unit I or MPa), in this example, determining the effective plate shape measurement characteristic point of roll band steel number according to band steel specification and plate profile instrument size is 20.
(3) 1000 groups of process datas in this example are carried out to sequential processing, processing rule is:
That group data minimum by DataID value in 1000 groups of cold-rolling mill input/output procedure data that obtain in previous step start, if DataID is i (i ∈ { 1,200000}) and two groups of data of i+1 belong to above-mentioned 1000 groups of process datas simultaneously, according to the ascending order of DataID value by u
ij(i ∈ 1 ..., 200000}; J=1,2,3) assignment is to U
kj(k=1 ..., N; J=1,2,3), simultaneously by δ
ij-δ
(i+1)j assignment is to F
kj(k=1 ..., 256; J=1,2,3), the data group number that in this example, effective cold-rolling mill input/output procedure data is carried out obtaining after sequential processing is 256 groups.
(4) set up the plate shape control action mechanism model based on data-driven:
Utilize the N=256 group cold-rolling mill input/output procedure data U obtaining after sequential processing in step (3)
ij(i=1 ..., 256; J=1,2,3) and F
ij(i=1 ..., 256; J=1 ..., n; N=20) set up described plate shape control action mechanism model:
In formula: r
ij(i=1 ..., N; J=1 ..., n) representing that in model, i group cold-rolling mill input/output procedure data are in the random error at j effective plate shape measurement characteristic point place, it obeys random normal distribution.
(5) set up the objective optimization function J of following cold-rolling mill shape regulation and control efficiency coefficient off-line self-learning method:
Utilize 256 groups of cold-rolling mill inputoutput data U in this example
ij(i=1 ..., 256; J=1,2,3) and F
ij(i=1 ..., 256; J=1 ..., 20) and the information that provides, ask for and can make above-mentioned objective optimization function J get the Mill shape regulation and control efficiency coefficient E of minimum of a value
kj(k=1,2,3; J=1 ..., 20) and be main target of the present invention.
The objective optimization function J that the plate shape control action mechanism model based on data-driven of setting up in conjunction with previous step and this step propose, when the present invention utilizes least-squares algorithm calculating objective optimization function J to get minimum of a value, cold-rolling mill shape regulation and control efficiency coefficient, adopts advanced matrix Orthogonal Decomposition algorithm to calculate and makes objective optimization function J get the Mill shape regulation and control efficiency coefficient E of minimum of a value in this example
kj(k=1,2,3; J=1 ..., 20):
First by U
ij(i=1 ..., 256; J=1,2,3) 256 × 3 dimension matrixes that form carry out Gram-Schmit Orthogonal Decomposition:
Then utilize the matrix computations cold-rolling mill shape regulation and control efficiency coefficient matrix after Gram-Schmit Orthogonal Decomposition:
In formula, there is N=256, n=20.
The data field of Fig. 3 has provided the self study result of calculation of this example.For the characteristic of the result of calculation of performance self study more intuitively, provide the plate shape regulation and control efficiency coefficient distribution block diagram of roller declination, the positive and negative roller of working roll, the positive roller of intermediate calender rolls three kinds of devices on the right of system interface, can better offer the effect that technical staff carries out self study result of calculation and differentiate.
(6) judge whether result of calculation meets the requirements:
Objective optimization function in cold-rolling mill shape regulation and control efficiency coefficient substitution steps (5) before off-line learning is calculated to objective optimization functional value J
1, calculate objective optimization functional value J at the objective optimization function that the Mill shape after off-line learning is regulated and controled in efficiency coefficient substitution steps (5)
2.If there is J
1>J
2, illustrating that off-line self study has improved the precision of Mill shape regulation and control efficiency coefficients, this off-line learning meets the requirements, and goes to step (7); Otherwise, illustrating that off-line self study has not improved the precision of Mill shape regulation and control efficiency coefficients, this off-line learning is undesirable, and increase goes to step (2) after counting Num for the cold-rolling mill inputoutput data group of off-line self study again.In this example, there is J
1=1812.7 and J
2=222.7, can find out J
1be far longer than J
2, this namely means before plate shape after off-line self study regulation and control efficiency coefficient is compared study and improves a lot aspect precision, this off-line self study result of calculation meets the requirements.
(7) the cold-rolling mill shape regulation and control efficiency coefficient calculating in step (6) is saved in to plate shape Computer Database, replaces original cold-rolling mill shape regulation and control efficiency coefficient, for the plate shape control of same specification belt steel rolling process later.
The beneficial effect that obtained in this example in order to show more clearly the inventive method, we utilize formula here:
represent that cold-rolling mill shape regulation and control efficiency coefficient is for 256 groups of Deviation Indices functions that cold-rolling mill inputoutput data exists at j plate shape characteristic point place in this example, the above-mentioned Deviation Indices function of cold-rolling mill shape regulation and control efficiency coefficient substitution after the cold-rolling mill shape regulation and control efficiency coefficient before respectively off-line self study being calculated and off-line self study are calculated.Fig. 4 has provided off-line self study and has calculated 20 plate shape characteristic point place Deviation Indices function comparison diagrams of this example of front and back.As seen from Figure 4, the inventive method has significantly improved the precision of cold-rolling mill shape regulation and control efficiency coefficients.It needs to be noted, the cold-rolling mill shape regulation and control efficiency coefficient before off-line self study is calculated is larger in steel edge portion region difference, and the reduction that this can cause steel edge portion control accuracy causes existing in production process broken belt danger.After calculating through off-line self study; in this example, the precision of the cold-rolling mill shape at all 20 plate shape characteristic point places regulation and control efficiency coefficient all improves a lot as seen from Figure 4; and the increase rate maximum in steel edge portion region; can effectively solve and cause the technical problem that cold-rolled steel strip products plate shape control accuracy is undesirable, the production accidents such as tape break stop even occur because efficiency coefficient precision is not high, fully prove validity and the practical value of the inventive method.
Above embodiment is only for calculating thought of the present invention and feature are described, its object is to make those skilled in the art can understand content of the present invention and implement according to this, and protection scope of the present invention is not limited to above-described embodiment.So the disclosed principle of all foundations, equivalent variations or the modification that mentality of designing is done, all within protection scope of the present invention.
Claims (10)
1. an offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill, it is characterized in that comprising: the plate shape control action modelling by mechanism module of off-line self study parameter setting module, cold-rolling mill input/output procedure data read module, process data sequential processing module, data-driven, cold-rolling mill shape regulation and control efficiency coefficient computing module, result of calculation are passed judgment on and processing module, and they are linked in sequence successively; Described module is all by carrying out data Preliminary screening and sequential processing to cold-rolling mill input/output procedure data according to rolling forward pull group, set up plate shape control action mechanism model and objective optimization function based on data-driven, Mill shape regulation and control efficiency coefficient when calculating makes objective optimization function get minimum of a value, realizes the self study of High Precision Cold Rolling Mill plate shape regulation and control efficiency coefficient off-line.
2. offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill according to claim 1, it is characterized in that described off-line self study parameter setting module, this module, for realizing the initial parameter set-up function of off-line self learning system, comprising: band steel specification, rolling forward pull group, importing creation data group are counted Num.
3. offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill according to claim 1, it is characterized in that described cold-rolling mill input/output procedure data read module, this module is for receiving the parameter band steel specification that described off-line self study parameter setting module sets, rolling forward pull group, import creation data group and count Num, according to the parameter band steel specification receiving, rolling forward pull group, importing creation data group counts and in Num slave plate shape Computer Database, reads the cold-rolling mill input/output procedure data for this off-line self study, the cold-rolling mill input/output procedure data that read are to meet the selected Num group data with steel specification and rolling forward pull group condition simultaneously, each group data inclusion information has: the regulated quantity of the online regulation device of each plate shape in corresponding control cycle, rolling forward pull size in corresponding control cycle, belt plate shape deviation profile signal when corresponding control cycle starts, the sequential numbering DataID of corresponding control cycle.
4. offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill according to claim 3, it is characterized in that in described cold-rolling mill input/output procedure data read module, in plate shape Computer Database, the assignment rule of the sequential of corresponding control cycle numbering DataID is: according to acquisition time sequencing, process data is carried out to process data numbering, the DataID=1 of first control cycle, the DataID=2 of second control cycle,, by that analogy;
When causing the cold rolling roll coil of strip not continue to stablize high-speed rolling due to acceleration and deceleration or roll change reason, temporarily stop said process data storage procedure; In the time recovering to stablize high-speed rolling, proceed process data storage, if and the DataID=i of last group process data of last process data storage, the storage of this secondary data starts to proceed storage according to acquisition time sequencing from DataID=i+2, the DataID value of follow-up each group of process data is respectively i+3,, by that analogy.
5. offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill according to claim 1, it is characterized in that described process data sequential processing module, the group of the Num for this off-line self study cold-rolling mill input/output procedure data that this module reads for receiving described cold-rolling mill input/output procedure data read module, and the sequential numbering DataID value according to each group of data is carried out further sequential processing to Num group process data, processing rule is: from above-mentioned Num group process data, those minimum group data of DataID value start, if being respectively two groups of process datas of i and i+1, DataID value belongs to above-mentioned Num group process data simultaneously, according to the ascending order of DataID value by u
ijassignment is to U
kj,simultaneously by δ
ij-δ
(i+1) jassignment is to F
kj,
In described symbol, i ∈ 1,2,3 ...; J=1 ..., m; K=1 ..., N; J=1 ..., m; Wherein m represents the online regulation device number of plate shape of cold-rolling mill configuration, and N is that this module carries out to effective cold-rolling mill input/output procedure data the data amount check obtaining after sequential processing.
6. offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill according to claim 1, it is characterized in that the plate shape control action modelling by mechanism module of described data-driven, this module is for receiving by process data U after the sequential processing of described process data sequential processing module output
kjand F
kjset up with the plate shape control action mechanism model based on data-driven; U
kjin, k=1 ..., N, j=1 ..., m; F
kjin, k=1 ..., N, j=1 ..., m;
The plate shape control action mechanism model of described data-driven is:
In formula: r
kjrepresent that in model, k group cold-rolling mill input/output procedure data are in the random error at j effective plate shape measurement characteristic point place, it obeys random normal distribution, wherein k=1 ..., N, j=1 ..., n.
7. offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill according to claim 6, it is characterized in that described cold-rolling mill shape regulation and control efficiency coefficient computing module, the plate shape control action mechanism model of the data-driven that the plate shape control action modelling by mechanism module of this module based on described data-driven provides, set up the objective optimization function J of following cold-rolling mill shape regulation and control efficiency coefficient off-line self-learning method:
Then the E while utilizing least-squares algorithm calculating objective optimization function J to get minimum of a value
kj, E
kjbe the cold-rolling mill shape regulation and control efficiency coefficient of the online regulation device of k kind plate shape at j plate shape characteristic point place, wherein k=1 ..., m, j=1 ..., n, n is the plate shape characteristic point number of roll with steel.
8. offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill according to claim 7, it is characterized in that in described cold-rolling mill shape regulation and control efficiency coefficient computing module cold-rolling mill shape regulation and control efficiency coefficient E while utilizing least-squares algorithm calculating objective optimization function J to get minimum of a value
kjtime,
Adopt the following direct inversion calculation algorithm of routine:
Or,
Adopt following matrix Orthogonal Decomposition algorithm:
First by U
ij(i=1 ..., N; J=1 ..., N × m dimension matrix m) forming carries out Gram-Schmit Orthogonal Decomposition:
Then utilize the matrix computations cold-rolling mill shape regulation and control efficiency coefficient matrix after Gram-Schmit Orthogonal Decomposition:
9. offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill according to claim 6, it is characterized in that in the plate shape control action modelling by mechanism module of described data-driven, effective measuring section number that roll laterally covers contact plate profile instrument by roll with steel with the plate shape characteristic point number of steel is determined.
10. according to the offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill described in claim 1 or 7 or 8, it is characterized in that described result of calculation judge and processing module, this module is by the cold-rolling mill shape regulation and control efficiency coefficient E before off-line learning
kjdescribed in substitution, in the objective optimization function of cold-rolling mill shape regulation and control efficiency coefficient computing module, calculate the front functional value J of this off-line learning
1, then will in the objective optimization function of cold-rolling mill shape regulation and control efficiency coefficient computing module described in the Mill shape regulation and control efficiency coefficient substitution after off-line learning, calculate functional value J after off-line learning
2, then pass judgment on and process:
If there is J
1>J
2illustrate that this off-line self study has improved the precision of Mill shape regulation and control efficiency coefficients, think that this off-line learning meets the requirements, preserve the machine result of calculation to plate shape Computer Database, replace original cold-rolling mill shape regulation and control efficiency coefficient, for the plate shape control of same specification belt steel rolling process later; Otherwise, illustrate that this off-line self study has not improved the precision of Mill shape regulation and control efficiency coefficients, this off-line self study is undesirable, after counting Num, the importing creation data group of the described off-line self study parameter setting module of now selection increase re-starts an off-line self study, until obtain satisfied off-line self study result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210012408.1A CN102527737B (en) | 2012-01-16 | 2012-01-16 | Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210012408.1A CN102527737B (en) | 2012-01-16 | 2012-01-16 | Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill |
Publications (2)
Publication Number | Publication Date |
---|---|
CN102527737A CN102527737A (en) | 2012-07-04 |
CN102527737B true CN102527737B (en) | 2014-06-25 |
Family
ID=46336464
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210012408.1A Expired - Fee Related CN102527737B (en) | 2012-01-16 | 2012-01-16 | Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102527737B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104971949B (en) * | 2014-04-10 | 2017-02-01 | 鞍钢股份有限公司 | Cold-strip steel shape control method based on embedded computer |
CN105710136B (en) * | 2016-02-03 | 2018-03-06 | 首钢总公司 | A kind of non-orientation silicon steel production control method and system |
CN108480405B (en) * | 2018-04-16 | 2020-05-05 | 东北大学 | Cold-rolled plate shape regulation and control efficiency coefficient obtaining method based on data driving |
CN109675931B (en) * | 2019-01-25 | 2020-04-07 | 燕山大学 | Self-learning method and system for plate-shaped regulation and control efficiency coefficient |
CN113070349B (en) * | 2021-03-29 | 2023-05-12 | 常熟科弘材料科技有限公司 | Plate type automatic adjusting system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10049260A1 (en) * | 2000-10-05 | 2002-04-25 | Achenbach Buschhuetten Gmbh | Pre-adjusting and regulating the planarity of a rolled strip comprises influencing the roll gap profile using adjusting values for the profile, adjusting the tensile stress |
CN101648216A (en) * | 2009-09-11 | 2010-02-17 | 燕山大学 | Method for setting plate shape and plate convexity off-line prediction of PC rolling mill |
CN101683659A (en) * | 2008-09-28 | 2010-03-31 | 宝山钢铁股份有限公司 | Integrated control method of cold-rolling strip steel flatness and lateral thickness difference |
CN101920269A (en) * | 2009-06-11 | 2010-12-22 | 鞍钢股份有限公司 | Method for optimizing regulating and controlling efficiency coefficient of board shape controlling actuator of cold rolling mill |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004141888A (en) * | 2002-10-22 | 2004-05-20 | Jfe Steel Kk | Method for manufacturing band-shaped thin steel sheet |
JP2004154830A (en) * | 2002-11-07 | 2004-06-03 | Yaskawa Electric Corp | Automatic control method for shape in width direction of cold rolling machine |
-
2012
- 2012-01-16 CN CN201210012408.1A patent/CN102527737B/en not_active Expired - Fee Related
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10049260A1 (en) * | 2000-10-05 | 2002-04-25 | Achenbach Buschhuetten Gmbh | Pre-adjusting and regulating the planarity of a rolled strip comprises influencing the roll gap profile using adjusting values for the profile, adjusting the tensile stress |
CN101683659A (en) * | 2008-09-28 | 2010-03-31 | 宝山钢铁股份有限公司 | Integrated control method of cold-rolling strip steel flatness and lateral thickness difference |
CN101920269A (en) * | 2009-06-11 | 2010-12-22 | 鞍钢股份有限公司 | Method for optimizing regulating and controlling efficiency coefficient of board shape controlling actuator of cold rolling mill |
CN101648216A (en) * | 2009-09-11 | 2010-02-17 | 燕山大学 | Method for setting plate shape and plate convexity off-line prediction of PC rolling mill |
Non-Patent Citations (4)
Title |
---|
冷轧机板形调节能力分析方法的研究与应用;闫沁太等;《机械工程学报》;20110228;第47卷(第4期);第77-81页 * |
带钢冷连轧板形功效系数自学习计算模型;张殿华等;《钢铁》;20100331;第45卷(第3期);第52-56页 * |
张殿华等.带钢冷连轧板形功效系数自学习计算模型.《钢铁》.2010,第45卷(第3期), |
闫沁太等.冷轧机板形调节能力分析方法的研究与应用.《机械工程学报》.2011,第47卷(第4期), |
Also Published As
Publication number | Publication date |
---|---|
CN102527737A (en) | 2012-07-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102553941B (en) | Off-line self-learning method of plate-shaped regulating efficiency coefficient of cold rolling mill | |
CN102527737B (en) | Offline self-learning system for strip shape control efficiency coefficient of cold-rolling mill | |
Hu et al. | Optimization of metal rolling control using soft computing approaches: a review | |
Lu et al. | Prediction and analysis of cold rolling mill vibration based on a data-driven method | |
CN101320031B (en) | Austenitic stainless steel accurate steel strip performance prediction model and cold rolling process planning thereof | |
CN102632085B (en) | Cold-rolled strip steel plate shape control system and method | |
CN104808587B (en) | A kind of mobility statistical method based on machining apparatus running status | |
CN102658297B (en) | Self-learning method for improving quality of first band steel plate shape with changed specification | |
CN100577315C (en) | Device for forecasting and controlling material quality of roll line | |
CN202606511U (en) | Cold rolled steel plate shape feedforward-feedback cooperative control system | |
CN103268082A (en) | Thermal error modeling method based on gray linear regression | |
CN106540968B (en) | The compensation method of cold rolled sheet shape measured value and device | |
CN105929812A (en) | Strip steel hot continuous rolling quality fault diagnosis method and device | |
CN103394522B (en) | Onsite testing method of control efficacy coefficient of strip shapes of cold-rolled strip steel | |
CN104898562A (en) | Modeling method of thermal error compensation of numerically-controlled machine tool | |
CN102641896B (en) | Gauge and flatness comprehensive control system of cold rolled steel sheet | |
CN115121626B (en) | Hot-rolled strip steel transient hot roll shape forecasting method based on error compensation | |
Wang et al. | A milling tool wear monitoring method with sensing generalization capability | |
CN105013835A (en) | Original roller seam setting method based on thermal crown in ultra-thin strip rolling conducted by cold continuous rolling unit | |
CN102641897B (en) | Gauge and flatness comprehensive control method of cold rolled steel sheet | |
CN109675931B (en) | Self-learning method and system for plate-shaped regulation and control efficiency coefficient | |
CN105706010A (en) | Production line simulation device | |
CN101690949A (en) | Tertiary panel-shape closed-loop control method | |
CN101927268A (en) | Method for controlling thickness of tandem cold-rolled striped steel | |
KR100841888B1 (en) | Rolling line material quality prediction and control apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140625 Termination date: 20200116 |
|
CF01 | Termination of patent right due to non-payment of annual fee |